• LongerDonger
    link
    English
    410 months ago

    You can already run LLMs on consumer hardware. They’re slow, but they definitely work. Mine is midrange from about 5 years ago and I can run a small one at a pretty reasonable speed or a medium (but “smarter”) one quite slowly at roughly 2 seconds per token.

    • @Rando2
      link
      English
      2
      edit-2
      8 months ago

      deleted by creator